llvm/test/CodeGen/AMDGPU/llvm.amdgcn.readfirstlane.ll
Changpeng Fang fb717b4b98 AMDGCN/SI: Implement readlane/readfirstlane intrinsics
Summary:
  This patch implements readlane/readfirstlane intrinsics.
TODO: need to define a new register class to consider the case
that the source could be a vector register or M0.

Reviewed by:
  arsenm and tstellarAMD

Differential Revision:
  http://reviews.llvm.org/D22489

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@279660 91177308-0d34-0410-b5e6-96231b3b80d8
2016-08-24 20:35:23 +00:00

36 lines
1.3 KiB
LLVM

; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -verify-machineinstrs < %s | FileCheck %s
declare i32 @llvm.amdgcn.readfirstlane(i32) #0
; CHECK-LABEL: {{^}}test_readfirstlane:
; CHECK: v_readfirstlane_b32 s{{[0-9]+}}, v{{[0-9]+}}
define void @test_readfirstlane(i32 addrspace(1)* %out, i32 %src) #1 {
%readfirstlane = call i32 @llvm.amdgcn.readfirstlane(i32 %src)
store i32 %readfirstlane, i32 addrspace(1)* %out, align 4
ret void
}
; CHECK-LABEL: {{^}}test_readfirstlane_imm:
; CHECK: v_mov_b32_e32 [[VVAL:v[0-9]]], 32
; CHECK: v_readfirstlane_b32 s{{[0-9]+}}, [[VVAL]]
define void @test_readfirstlane_imm(i32 addrspace(1)* %out) #1 {
%readfirstlane = call i32 @llvm.amdgcn.readfirstlane(i32 32)
store i32 %readfirstlane, i32 addrspace(1)* %out, align 4
ret void
}
; TODO: m0 should be folded.
; CHECK-LABEL: {{^}}test_readfirstlane_m0:
; CHECK: s_mov_b32 m0, -1
; CHECK: v_mov_b32_e32 [[VVAL:v[0-9]]], m0
; CHECK: v_readfirstlane_b32 s{{[0-9]+}}, [[VVAL]]
define void @test_readfirstlane_m0(i32 addrspace(1)* %out) #1 {
%m0 = call i32 asm "s_mov_b32 m0, -1", "={M0}"()
%readfirstlane = call i32 @llvm.amdgcn.readfirstlane(i32 %m0)
store i32 %readfirstlane, i32 addrspace(1)* %out, align 4
ret void
}
attributes #0 = { nounwind readnone convergent }
attributes #1 = { nounwind }